CUA is a Automation MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent computer-Use Agent — let LLMs control computers, click buttons, type text, navigate GUIs. Install in 1 minute with mcpizy install cua.
Automation
Computer-Use Agent — let LLMs control computers, click buttons, type text, navigate GUIs.
mcpizy install cuanpx -y @cua/mcp-serverWeb AI agents for browser automation. Navigate, extract, and interact with any website.
Human-in-the-loop platform for AI agent approval requests. Add human checkpoints to workflows.
Schedule, list, and manage cron jobs and recurring tasks from AI agents via MCP.
Trigger n8n workflows and manage executions for low-code automation from AI agents.
If CUA doesn't fit your stack, these Automation MCP servers solve similar problems.
Turn Make scenarios into callable tools for AI assistants. Connect 1,500+ apps with automation.
Interact with any SaaS application on behalf of customers. Universal API integration layer.
Arbitrary code execution platform for LLMs. Run Python, JavaScript, and more in sandboxes.
The CUA MCP server is an Automation Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents computer-Use Agent — let LLMs control computers, click buttons, type text, navigate GUIs. It exposes CUA's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install cua` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @cua/mcp-server` and restarting Claude Code.
Yes. The CUA MCP server is free and open source (see the GitHub repository linked on this page). You may still need a CUA account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can computer-Use Agent — let LLMs control computers, click buttons, type text, navigate GUIs directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run CUA operations, inspect results, chain CUA with other MCP servers (see our Workflow Recipes), and automate repetitive automation tasks without leaving your editor.